© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92286
    Prev
    Next
    INDEX
    Explanations

    commas and periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usually
    -1.11
    Usually
    -1.09
     Usually
    -1.05
    usually
    -1.02
    Typically
    -0.94
     suele
    -0.94
     brukar
    -0.93
     typically
    -0.90
     Often
    -0.85
     Typically
    -0.85
    POSITIVE LOGITS
     Or
    0.54
    hematical
    0.49
    Or
    0.48
    anze
    0.45
     yet
    0.45
    Sklici
    0.45
    acij
    0.44
    towym
    0.44
    licht
    0.43
    完全に
    0.43
    Activations Density 0.070%

    No Known Activations